Significance Editing in the Survey of Employment and Earnings Executive Summary
Bibliographic record
Abstract
Significance editing is a statistical technique which is used to prioritise and control the amount of input editing in a survey. The technique works on the premise that only those units which fire edit queries that are considered to be significant need to be edited. An edit query for a unit is considered to be significant if it is assigned a score above a prespecified cut-off value. The score is based on the expected effect on survey estimates caused by changing the unit's reported data to some value determined by the edit rule. The technique ensures that the bias due to not editing some of the survey forms is less than 10 % of the variance of the estimate at the state by industry division level. The introduction of significance editing in the survey of Average Weekly Earnings (AWE) was very successful, resulting in negligible effects on survey estimates and resource savings of between three and four staff years. This study has evaluated the effects on survey estimates and the resource savings that could be made by implementing the significance editing technique in the Survey of Employment and Earnings (SEE). A parallel run approach was used to make this assessment. Two separately maintained survey data files for the December quarter 1998 were used to produce estimates under the significance editing approach and under the current approach, and the two sets of estimates were compared. The results showed that applying the significance editing technique should have negligible effects on the SEE survey estimates. For estimates of gross quarterly
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.017 | 0.090 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".